Working fetch feeds and process raw urls

This commit is contained in:
Luciano Gervasoni
2025-03-13 18:23:28 +01:00
parent 61c31ee9aa
commit 7d7bce1e72
11 changed files with 318 additions and 136 deletions

View File

@@ -1,4 +1,4 @@
# Generated by Django 5.1.7 on 2025-03-07 16:56
# Generated by Django 5.1.7 on 2025-03-13 17:01
import django.db.models.deletion
from django.db import migrations, models
@@ -62,8 +62,8 @@ class Migration(migrations.Migration):
fields=[
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
('url', models.TextField(unique=True)),
('ts_fetch', models.DateTimeField()),
('status', models.TextField()),
('ts_fetch', models.DateTimeField(auto_now_add=True)),
('status', models.TextField(choices=[('raw', 'Raw'), ('error', 'Error'), ('valid', 'Valid'), ('unknown', 'Unknown'), ('invalid', 'Invalid'), ('duplicate', 'Duplicate')], default='raw')),
],
options={
'db_table': 'urls',
@@ -100,9 +100,16 @@ class Migration(migrations.Migration):
('title', models.TextField(blank=True, null=True)),
('description', models.TextField(blank=True, null=True)),
('content', models.TextField(blank=True, null=True)),
('valid_content', models.BooleanField(blank=True, null=True)),
('language', models.CharField(blank=True, max_length=2, null=True)),
('keywords', models.TextField(blank=True, null=True)),
('tags', models.TextField(blank=True, null=True)),
('authors', models.TextField(blank=True, null=True)),
('image_urls', models.TextField(blank=True, null=True)),
('image_main', models.TextField(blank=True, null=True)),
('images_url', models.TextField(blank=True, null=True)),
('videos_url', models.TextField(blank=True, null=True)),
('url_host', models.TextField(blank=True, null=True)),
('site_name', models.TextField(blank=True, null=True)),
],
options={
'db_table': 'url_content',